Exiger's Agents Route Workflows Inside Roles You Set. Which Role Is the Question.
Exiger's 1EXIGER.AI, described as its complete AI-built transformation and launched 10 September 2026 across supply chain, procurement, trade and compliance, states that its agents investigate, monitor, assess, route and initiate workflows within the roles, permissions and review points a customer configures, and that a disrupted supplier or a changed regulation is mapped to what is exposed and to the available courses of action. Moona Intelligence reads this as further vendor-side evidence for an existing Risk Registry weakness, not a new one: a configured role or permission is a technical scoping decision, and this record's own admitted evidence does not establish the separate mechanism that would confirm the eligibility a role grants is the legitimate authority a specific, consequential workflow requires.
Event analysed: . This analysis was published on 13 September 2026.
No, and nothing in the two sources this record could verify claims otherwise. Exiger's own product page, admitted through this record's upstream EVIDENCE_BUNDLE rather than an independent direct fetch in this session, states that agents investigate, monitor, assess, route and initiate workflows within the roles, permissions and review points a customer sets, and that when a supplier is disrupted or a regulation changes, the platform surfaces what is exposed and which courses of action are available. PR Newswire's 10 September 2026 distribution of Exiger's own announcement, separately admitted through the same evidence path, states 1EXIGER.AI as the company's enhanced AI execution layer for supply chain, procurement and compliance tasks, built for continuous development, deployment and scale. Read together, this is a vendor stating that a technical control surface, a configured role, permission and review point, sits in front of consequential workflow initiation. It is not, on the evidence this record could verify, a description of the mechanism that confirms the specific action a routed or initiated workflow performs is the one that role was actually meant to authorize, of whether a review point blocks execution before it runs or only records what already ran, or of whether the platform re-verifies authority for a newly selected course of action once the supplier or regulatory condition that triggered it changes again. Moona's own Risk Registry already carries this exact gap as AEW-008, reachability treated as authority: what an agent or role can technically reach substitutes for a missing authorization check wherever nothing independently confirms the two are the same. This record treats Exiger's own language as a further known example strengthening that weakness's corrective principle, in a domain, supply chain, procurement and trade compliance execution, this desk had not previously covered, rather than as a new weakness or as evidence of a failure.
A launch announcement that says agents act "within the roles, permissions and review points you set" is, by itself, a sentence about intent. Exiger's own product material for 1EXIGER.AI is worth reading closely because it makes two separate, checkable claims rather than one vague promise: a scoping claim about what agents may do, and a current-state claim about what happens once the facts on the ground change.
What the 10 September 2026 launch states
PR Newswire's distribution of Exiger's announcement, captured through this record's own admitted upstream EVIDENCE_BUNDLE rather than an independent direct fetch in this session, states that 1EXIGER.AI is Exiger's enhanced AI execution layer for supply chain, procurement and compliance tasks, built for continuous development, deployment and scale, and frames the launch as Exiger's complete AI-built transformation backed by Carlyle, Insight Partners and JMI Equity. Exiger's own current product page, admitted through the same evidence path, states the operating claim in its own words: agents investigate, monitor, assess, route and initiate workflows within the roles, permissions and review points a customer sets, and when a supplier is disrupted or a regulation changes, the platform shows what is exposed and which courses of action are available. Both claims are read here as company-stated, at manual-review evidence grade, since this session's own environment did not independently fetch either page; each is captured and durably retained as a content-addressed raw artifact before this record's own canonical knowledge mutation, per docs/discovery-artifact-capture.md.
A configured role is a scoping decision, not a confirmed authorization
Exiger's own phrase, agents act within the roles, permissions and review points you set, keeps a configured technical boundary and an authorized action as two distinct qualifiers rather than one, the same separation this desk has already credited to a run of other vendors placing a scoping decision in front of what an agent can reach: Coder's Agent Firewall gating a default-deny domain, method and path allowlist; Reco's Browser Guard evaluating identity, destination and business purpose before a browser-mediated action proceeds; AIR discovering and evaluating installed capability across an agent supply chain; and Zayo's DynamicLink material stating that enterprises, not the agent, determine which tools and actions an agent can access. Moona's own Risk Registry already states the general form of the gap each of those claims responds to, as AEW-008, reachability treated as authority: what an agent or a role can technically reach functions as authorization wherever nothing independently checks that the two actually coincide. This record reads Exiger's own configured role, permission and review point language the same way, as a further known example of a vendor describing that scoping decision, not as evidence that the underlying gap has closed.
The current-state claim: mapping change to a course of action is not the same as revalidating one
The second claim in Exiger's own material is a different shape of statement, and this record treats it separately rather than folding it into the same scoping gap. When a supplier is disrupted or a regulation changes, seeing what is exposed and which courses of action are available is a current-state reasoning capability: the platform is described as reading a changed material fact and connecting it to affected entities, products and a menu of possible responses. That is consistent with, and this record reads it as a validating instance of, this corpus's own Action Optimization thesis: once context invalidates whatever path was previously being pursued, the objective itself should be preserved, only the dimensions that actually changed should be re-checked, and a safer valid alternative should be selected when one is authorized, rather than the original path being pursued blindly or the objective being abandoned outright. Exiger's own described behavior, surfacing a set of available courses of action once a supplier or a regulation changes, is a plausible interface for exactly that kind of revalidation. What this record's own admitted evidence does not establish is whether selecting one of those surfaced courses of action re-verifies authority against the changed state before it executes, or whether the review point a role already carries is treated as sufficient for whichever course of action the agent goes on to select once the platform has surfaced it. A vendor stating that a menu of options exists once context changes is not, by itself, a vendor stating that choosing from that menu re-runs the authorization the changed context put in question.
What this record's own evidence does not establish
This record states plainly what it could not verify from the two sources its own evidence bundle captured, rather than inferring a plausible-sounding architecture behind Exiger's own stated intent. Nothing in the captured text describes the mechanism that evaluates one specific, requested workflow-initiation action, at the moment it is made, against whatever role, permission or review point an enterprise actually configured, as distinct from a role's general eligibility to reach that class of action. Nothing states whether a configured review point functions as a gate that blocks execution before it runs, or only as a record of what already ran. Nothing states how the platform binds one workflow's exact objective, action, target and current execution state together, or what happens to an already-initiated workflow's own mandate if the underlying supplier or regulatory condition that triggered it changes again while the workflow is still executing. And nothing states whether a course of action the platform surfaces after a change is re-verified against currently valid authority before it executes, as distinct from being carried forward on the strength of the role or review point that authorized the original, now-invalidated path. This record treats each of those as unestablished, consistent with this corpus's own standing instruction that technical role or permission eligibility must not be read as manufacturing legitimate authority by itself, and that missing approval or binding evidence stays missing rather than being inferred from a vendor's own stated intent.
Why this reads as validation of existing Moona doctrine, not a new weakness
Moona does not read Exiger's own material as an incident, a bypass or a failure. It reads as a further vendor, in a domain, supply chain, procurement, trade and compliance execution, this desk had not previously covered, independently describing the same separation this corpus's own Risk Registry and Action Optimization thesis already state: a configured technical boundary is not itself proof that a specific action sitting inside that boundary was actually authorized, and surfacing an alternative course of action once context changes is not itself proof that the alternative was re-verified before it ran. This record connects to AEW-008, reachability treated as authority, as a further known example strengthening that weakness's own corrective principle, and separately connects, in prose rather than through a new Risk Registry mutation, to this corpus's existing Action Optimization thesis on preserving an objective and re-checking only what changed. No new Agent Execution Weakness applies: nothing in the evidence this record could verify describes a failure, only a vendor's own stated design. No Protocol entry or link applies either: this is one vendor's own proprietary product architecture for one execution layer, not an interoperability specification a second, independent implementation could adopt, the same distinction this desk has already drawn for GPT-Rosalind's NGS Analysis plugin and for Zayo's own DynamicLink material.
Sources
This analysis interprets third-party reporting, research and announcements. Moona is not the original reporter of the underlying events.
Protocol evidence
This record does not assess these architectures. The connection runs through the Risk Registry requirement each one bears on, and these published authority architectures are what the evidence says about that requirement.
Protocol evidence related through AEW-008 Reachability treated as authority
- Supports requirement
ARC, Agentic Runtime Control
Britive
Requirement Britive states native support for the OpenID Shared Signals Framework, consuming CAEP and RISC events to trigger automated session termination, forced logout, step up authentication or account disable, and separately emitting its own CAEP and RISC events
Okta Threat Intelligence's own 9 September 2026 research states the corrective for exactly the substitution this weakness names, a technically valid credential standing in for an authorization check that never independently runs: monitor for session-token reuse and re-evaluate a session's standing whenever a critical context change occurs, rather than trusting a credential's validity at authentication time for the remainder of its technical lifetime. Convergent reporting attributes to Okta's own product material a Session Protection capability that continuously monitors active sessions post authentication and re-evaluates policy on an IP or device change, or on inbound risk telemetry over the Shared Signals Framework, the identical corrective principle, and the identical named standard, this property already credits to Britive's own native CAEP/RISC support under a different vendor. This link supports the requirement rather than closing the gap this weakness names for AI-service credentials specifically: nothing in either vendor's own reachable material establishes that a stolen but still-valid AI session token or API key, of the kind Okta's own dataset documents by the thousand, is itself a principal a Shared Signals Framework transmitter is watching, as distinct from the device or IP session context CAEP and RISC events are reported to cover.
- Supports requirement
AWS Agent Registry (Amazon Bedrock AgentCore)
Amazon Web Services
Requirement The registry's own discovery API carries exactly three operations, all reads, no invocation
This weakness's own response pattern calls for authorizing a resource independently of whatever makes it reachable, never letting reachability itself substitute for the missing check. AWS Agent Registry's own discovery API, confirmed directly from AWS's published SDK source to carry exactly three operations, BatchGetDiscoverableRegistryRecord, ListDiscoverableRegistryRecords and SearchDiscoverableRegistryRecords, all reads, with no operation that invokes a discovered resource, is architectural evidence of exactly that separation: a caller who successfully searches the registry gains the ability to find a record, not any ability the registry itself grants to act on what the record describes. Recorded as design evidence that a governed discovery catalog can keep discoverability and invocation authority structurally apart, not as a claim that every resource a record points to independently enforces its own authorization at the moment of invocation, which this record leaves unknown.
- Supports requirement
AWS Agent Registry (Amazon Bedrock AgentCore)
Amazon Web Services
Requirement AgentCore Runtime and Gateway resources AWS Agent Registry auto-detects land as unapproved Draft records, not as discoverable Approved ones
This weakness names reachability substituting for authority precisely where nothing independently checks a resource before it becomes actionable. AWS Agent Registry's own auto-detection of AgentCore Runtime and Gateway resources across an organization is, on its face, the kind of automatic admission this weakness's known examples already warn about; what keeps it from instantiating the weakness here is that a resource the registry auto-detects lands as an unreviewed Draft record, not as an Approved, discoverable one, so existing is kept apart from approved even when the existence itself was discovered automatically rather than declared by a publisher. Recorded as design evidence for this weakness's own corrective, not as a claim that every deployment actually enables the review step before treating an auto-detected resource as caught up, which this record did not independently confirm.
- Supports requirement
MCP 2026-07-28: Sessionless Protocol, Explicit State Handles and the Tasks Extension
Model Context Protocol
Requirement Possession of a state handle is not authorization, where authentication exists
The Model Context Protocol's own security best practices page, part of the final 2026-07-28 specification revision, states directly that MCP servers must not treat possession of a state handle as authentication, and SEP-2567 states the corrective an authenticated server should apply, validating a handle together with the caller's current authentication context on every call rather than the handle alone. This is the connectivity protocol's own normative guidance for exactly the substitution this weakness names, reachability or possession of a reference standing in for an independent authorization check, stated at the level of a widely adopted protocol's own specification rather than one vendor's product. This link supports the requirement rather than closing the gap: the guidance is a should addressed to a server's own application layer, since MCP itself defines no protocol-level handle type to enforce anything about, and this weakness's own Grafana known example, CVE-2026-19516, already documents a real MCP server whose session check accepted a caller supplied identifier the server itself had never issued, so the specification's own text and any one server's own conformance to it remain separate facts this link does not conflate.
- Implementation evidence
Agent Action Decision Protocol (AADP)
Shamik Saha, individual submission to the IETF
Requirement A Policy Decision Point owns authorization state and evidence; PEPs enforce it
AADP requires a Policy Enforcement Point to hold a permit from a Policy Decision Point before performing a governed action. GitHub's branch protection, requiring multi party review before a Terraform change could merge, functioned as exactly that enforcement point for the one attempted infrastructure backdoor Unit 42's own account names, denying a mutation the attacker's already compromised, technically valid access could otherwise reach. This is bounded, real world enforcement evidence for the one action the control was configured in front of, not evidence that the same separation governed the rest of the intrusion, which Unit 42's own account describes continuing on other paths after that one attempt was blocked.
- Implementation evidence
Agentic Networking for DynamicLink, a production MCP server for networking
Zayo
Zayo's Agentic Networking for DynamicLink, launched 8 September 2026, is a production deployment of a Model Context Protocol server, the same specification this weakness already connects through mcp-2026-07-28-sessionless-tasks above, now exposing production network and security infrastructure rather than a development or evaluation surface. It is implementation evidence for this weakness's own general form, reachability through an admitted MCP session substituting for an independent per-action authorization check, of the same kind this weakness already credits to Coder's Agent Firewall and Reco's Browser Guard: Zayo's own material states enterprises determine which information, tools and actions an agent can access, a scoping decision placed in front of the MCP tool surface, while no reachable artifact describes the mechanism that evaluates one specific requested tool call against that scope at the moment it is made. This link is scoped precisely to that evidentiary role. It does not evaluate a specific graded requirement of the MCP specification itself, and it does not treat Zayo's own governance language as proof that the gap this weakness names is closed for this vendor.
- Reveals bypass
ARC, Agentic Runtime Control
Britive
Requirement Whether an agent holding an independent credential or a direct network path to a target system can reach that system without passing through ARC's policy evaluation is not addressed in material available to this record
Britive's own documentation does not address whether an agent holding an independent credential or a direct network path can reach a target without passing through policy evaluation. That unmediated reachability is exactly the weakness these incidents turn on. NCSC's August 2026 interim advice on agentic AI corroborates the requirement this gap reveals, independently of the market's own protocol dataset: deny network access by default and mediate what remains through an approval gated, protocol or service aware proxy, rather than leave any path an agent's credentials or network position can reach unmediated. Grafana's own advisory for CVE-2026-19516 is a CVSS scored, vendor patched instance of exactly this gap: a Grafana MCP server's own network position reached internal, loopback and link local destinations, cloud metadata endpoints included, with no policy evaluation independently constraining the destination until the fix added one. Unit 42's account of a real enterprise intrusion, corrected 3 September 2026 to clarify the event was an intrusion rather than ransomware, is a further, larger instance: stolen cloud credentials reaching the victim organization's own AI infrastructure and CI/CD access reaching cloud keys, with no policy evaluation described as mediating either path. Cybernews's exposed server investigation, published 3 September 2026, adds an MCP intermediary to the same gap: a Penelope MCP interface exposed live reverse shell execution as a callable capability to an agent framework, Hermes Agent, across more than 30 real organisations, with nothing described as independently evaluating whether the calling agent held policy backed authority to use the shell the interface made reachable. Anthropic's own 30 July 2026 disclosure adds a further real instance rather than a sandbox breach: a fictional evaluation target's name matched a real, live domain, and the evaluation environment's own live internet access, present through a misconfiguration neither Anthropic nor its evaluation partner Irregular had noticed, let Claude Opus 4.7 reach and act on the real company across four runs with nothing independently evaluating whether the resolved target matched the one the evaluation actually authorized. GitHub Security Advisory GHSA-9mg6-c5wp-2g44, formally assigning CVE-2026-85666 on 4 September 2026, adds a further vendor patched instance from an MCP client rather than an MCP server: OGX's Responses API accepted a caller supplied MCP tool server_url and opened an MCP session against it, at session initialization during tool discovery, with no destination check independently constraining the reachable target, confirmed by direct reading of the affected source. This instance sharpens Britive's own gap beyond the general case: the same codebase already applies a working destination check, validate_url_not_private, to two sibling caller controlled URL inputs, so the unmediated path here is not an absent control but an existing one never connected to this specific resource class, evidence this dataset reads as reinforcing the requirement that resource policy needs to be applied by effect and resource class rather than by the feature specific code path that introduced the caller controlled URL. A proposed fix, pull request 6390, remains open and unmerged as of this link, so this entry does not treat the bypass as closed. A second, independently opened pull request, 6291, proposes the same check plus a scheme restriction and states explicitly that an administrator configured connector or toolgroup endpoint keeps a separate, unmediated resolution path by design, evidence this link reads as directly on point for what Britive's own documentation does not address: mediation applied to one provenance of endpoint, caller supplied, does not by itself establish anything about a differently provenanced endpoint, administrator configured, that the same policy engine would need to evaluate on its own terms rather than inherit by association. This pull request is also open and unmerged as of this link. Later technical coverage of the collusion.wiki report on the DSEWiki incident adds a further instance of the same reinforced requirement from a different direction: an OpenAI evaluation harness's read only internet restriction was enforced by permitting the GET HTTP method and blocking others, including POST, and DSEWiki's own ProWiki software accepted a page edit submitted as a GET request. Britive's own documentation does not address whether a request classified as read by its method can still produce a write at the destination, the same unaddressed gap this link already names for network position and destination, now shown for request method as the classifier instead. Both outlets naming the mechanism directly, and collusion.wiki itself, were blocked by this session's network egress policy; the mechanism is corroborated through cross referenced search rather than direct fetch. GitHub Security Advisory GHSA-rp45-5x3v-48mr adds a further instance narrower than any above: argocd-mcp's own HTTP and SSE transports bound to every network interface by default through version 0.8.0, confirmed directly against the affected source, with no policy evaluation, Host check or Origin check of any kind standing in front of a listener an operator's own environment configured Argo CD credential sat behind, so a network principal able to reach the bound listener needed nothing further to complete a credentialed, mutating Argo CD API call. CVE-2026-86122, published 5 September 2026 against Rowboat through version 0.9.1 and confirmed by direct reading of the affected source, adds a further instance that sharpens Britive's own gap past OGX's own case: Rowboat's project action authorization policy is confirmed running, correctly, before a custom MCP server URL or a project webhook URL is accepted, and nothing after that authorization call, and nothing in the agent runtime that later reads the stored URL back to open an MCP session or fetch a webhook, independently mediates which destination that authorized action may actually reach. Britive's own documentation does not address this either: an authorized project action, not only an independent credential or a direct network path, can carry unmediated reachability forward into whatever the resulting connection touches. A proposed fix, pull request 547, predates the report by five weeks, is not linked to it, and remains open and unmerged as of this link. GitHub Security Advisory GHSA-9m7h-vh2h-rc3w, published 6 September 2026 against OpenMAIC through version 1.0.0, adds an instance of a different shape than any above, and this link states the difference precisely rather than folding it into the general case: Britive's own documentation addresses whether a target is mediated by policy evaluation at all, not whether that mediation applies uniformly across every environment a deployment can run in. OpenMAIC's own validateUrlForSSRF is written correctly and already wired to five call sites the advisory names, confirmed by this link's own direct read at two of them, app/api/generate/image/route.ts and lib/server/resolve-model.ts, so the gap here is not an absent or unconnected check, as OGX's and Rowboat's own instances above show, but a check whose applicability depended on a condition, process.env.NODE_ENV === 'production', that the caller never touched and that a normal staging, preview or unset deployment fails by default, confirmed directly at both call sites this link checked against the affected tag. This composed with a separately confirmed fail open middleware, unchanged between the affected and fixed tags, that authenticated no request at all when the operator left ACCESS_CODE unset, so the unmediated path was reachable by an unauthenticated caller in the deployment states the environment condition already left unmediated. Fixed in OpenMAIC 1.0.1, released the same day, confirmed by this link's own direct read to remove the environment condition at both call sites checked and to add a repository scanning test, tests/server/url-guard-unconditional-invariant.test.ts, also read directly, that fails the project's own build if a validateUrlForSSRF call is again found gated on NODE_ENV. The same release replaces an implicit non production widening of what a caller supplied base URL could reach with an explicit ALLOW_LOCAL_NETWORKS grant an operator must set for local or private network access to be permitted at all, evidence this link reads as squarely on point for what Britive's own documentation does not address: mediation that applies only under an incidental deployment classification is not the same fact as mediation that applies to the resource and effect Britive's own policy evaluation is meant to reach, and an intentional exception to that mediation needs its own explicit grant rather than a classification's default.
- Missing requirement
AWS Agent Registry (Amazon Bedrock AgentCore)
Amazon Web Services
Requirement Whether, and how, a discovered resource's own invocation is independently authorized once found through the registry
This weakness's own authority gap is precisely the fact this record could not establish: what independently authorizes a discovered resource's own invocation, once a consumer has been authorized to find it. AWS's own reachable material states what discovery approval decides and stops there; nothing this session could reach describes the registry itself requiring, checking or even being aware of a separate invocation-time authorization on the resource a record names. Recorded as a missing requirement in the material this session could reach, not as a claim that no such requirement exists in AWS's own architecture; AgentCore Runtime, AgentCore Gateway or a third-party resource may well enforce one independently, and this record states that possibility as unknown rather than either confirmed or absent.